Abstract
This paper presents a prediction method of fish movement based on learning its movement by using the Neural Network. The position of a fish is obtained by model-based matching and gazing-GA in real-time. The back-propagation is used for learning and predicting the movement of fish, where fish position is used as the input/teaching signal. The architecture and the internal parameter of the Neural Network are determined by basic experiments which use the simulated movement of fish. Experimental results using a swimming fish show that the proposed method can predict the movement of fish.
| Original language | English |
|---|---|
| Pages | 2400-2405 |
| Number of pages | 6 |
| Publication status | Published - Dec 1 2005 |
| Externally published | Yes |
| Event | SICE Annual Conference 2005 - Okayama, Japan Duration: Aug 8 2005 → Aug 10 2005 |
Other
| Other | SICE Annual Conference 2005 |
|---|---|
| Country | Japan |
| City | Okayama |
| Period | 8/8/05 → 8/10/05 |
Keywords
- Back-propagation
- Gazing-GA
- Neural Network
- Visual Sarvoing
ASJC Scopus subject areas
- Control and Systems Engineering
- Computer Science Applications
- Electrical and Electronic Engineering
Fingerprint Dive into the research topics of 'Learning of fish movement pattern by neural network'. Together they form a unique fingerprint.
Cite this
Takezawa, Y., Suzuki, H., Minami, M., & Mae, Y. (2005). Learning of fish movement pattern by neural network. 2400-2405. Paper presented at SICE Annual Conference 2005, Okayama, Japan.